© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38023
    Prev
    Next
    INDEX
    Explanations

    for everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    寻常
    -0.92
    દ
    -0.88
    MatInputModule
    -0.86
     akár
    -0.85
    ്യ
    -0.85
     ThemeData
    -0.85
     parseFrom
    -0.84
    ustomed
    -0.84
    ACGIH
    -0.83
    ategor
    -0.81
    POSITIVE LOGITS
     everyone
    10.06
     everybody
    8.00
    everyone
    7.69
    Everyone
    7.41
     Everyone
    6.97
    everybody
    6.13
    Everybody
    5.91
     EVERYONE
    5.88
     Everybody
    5.66
     iedereen
    5.06
    Activations Density 0.288%

    No Known Activations